Three Modern Roles for Logic in AI

04/18/2020
by   Adnan Darwiche, et al.
24

We consider three modern roles for logic in artificial intelligence, which are based on the theory of tractable Boolean circuits: (1) logic as a basis for computation, (2) logic for learning from a combination of data and knowledge, and (3) logic for reasoning about the behavior of machine learning systems.

READ FULL TEXT

page 1

page 3

page 8

page 10

research
04/08/2019

Fifty years of Hoare's Logic

We discuss a history of Hoare's logic....
research
06/15/2020

Symbolic Logic meets Machine Learning: A Brief Survey in Infinite Domains

The tension between deduction and induction is perhaps the most fundamen...
research
08/06/2019

Logic could be learned from images

Logic reasoning is a significant ability of human intelligence and also ...
research
07/03/2020

On Symbolically Encoding the Behavior of Random Forests

Recent work has shown that the input-output behavior of some machine lea...
research
07/09/2018

AI Reasoning Systems: PAC and Applied Methods

Learning and logic are distinct and remarkable approaches to prediction....
research
02/18/2021

Combinators and the Story of Computation

We discuss the role of combinators in the development of the modern conc...
research
06/05/2020

LGML: Logic Guided Machine Learning

We introduce Logic Guided Machine Learning (LGML), a novel approach that...

Please sign up or login with your details

Forgot password? Click here to reset